MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation

TL;DR

This paper introduces MDT-A2G, a novel Masked Diffusion Transformer for co-speech gesture generation that improves temporal reasoning, integrates multi-modal data, and significantly accelerates both learning and inference speeds.

Contribution

The paper presents a new Masked Diffusion Transformer architecture for gesture generation, enhancing temporal relation learning and multi-modal integration, with faster training and inference.

Findings

Over 6× faster learning speed compared to traditional diffusion transformers.

Inference speed increased by 5.7× over standard diffusion models.

Achieves coherent and realistic gesture generation.

Abstract

Recent advancements in the field of Diffusion Transformers have substantially improved the generation of high-quality 2D images, 3D videos, and 3D shapes. However, the effectiveness of the Transformer architecture in the domain of co-speech gesture generation remains relatively unexplored, as prior methodologies have predominantly employed the Convolutional Neural Network (CNNs) or simple a few transformer layers. In an attempt to bridge this research gap, we introduce a novel Masked Diffusion Transformer for co-speech gesture generation, referred to as MDT-A2G, which directly implements the denoising process on gesture sequences. To enhance the contextual reasoning capability of temporally aligned speech-driven gestures, we incorporate a novel Masked Diffusion Transformer. This model employs a mask modeling scheme specifically designed to strengthen temporal relation learning among sequence gestures, thereby expediting the learning process and leading to coherent and realistic motions. Apart from audio, Our MDT-A2G model also integrates multi-modal information, encompassing text, emotion, and identity. Furthermore, we propose an efficient inference strategy that diminishes the denoising computation by leveraging previously calculated results, thereby achieving a speedup with negligible performance degradation. Experimental results demonstrate that MDT-A2G excels in gesture generation, boasting a learning speed that is over 6$\times$ faster than traditional diffusion transformers and an inference speed that is 5.7$\times$ than the standard diffusion model.